© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 21908
    Prev
    Next
    INDEX
    Explanations

    special characters in academic text

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iecie
    -0.07
    ç¡®åĪĩ
    -0.07
    вне
    -0.07
     Merek
    -0.07
     '(
    -0.07
    endar
    -0.07
    æŃ£å¥½
    -0.07
    èĿł
    -0.07
     Chow
    -0.06
    åĪļ好
    -0.06
    POSITIVE LOGITS
    egas
    0.08
     sexi
    0.07
    tif
    0.07
    ä¹ĭåIJİçļĦ
    0.07
     –**
    0.07
    uus
    0.07
    ubin
    0.07
    à°¿à°ķ
    0.07
     –
    0.06
    ä¹ĭå¾Į
    0.06
    Activations Density 0.037%

    No Known Activations